{"id":"W6966799482","doi":"10.48410/m2ae-vj76","title":"Supplementary code data files for the thesis \"A Population-Based Approach to Genomic Island Analysis\"","year":2023,"lang":"en","type":"dataset","venue":"Summit, the SFU Research Repository","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Contig; Genome; ENCODE; Pathogenicity island; Population; Cluster analysis; Data integration; Source code; Genomics; Salmonella enterica","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01561873,0.0008500707,0.001108806,0.002194486,0.003627386,0.001240891,0.01283252,0.0004401096,0.0001963513],"category_scores_gemma":[0.002352445,0.0005179421,0.0007389507,0.004333583,0.0006198628,0.00018266,0.003701759,0.002041545,0.001663907],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00118641,"about_ca_system_score_gemma":0.001229388,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.0895259,"about_ca_topic_score_gemma":0.1268909,"domain_scores_codex":[0.986371,0.003860327,0.001290392,0.002530875,0.003941532,0.002005807],"domain_scores_gemma":[0.9723476,0.01285676,0.0005285587,0.01322619,0.0006366989,0.0004042025],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0005886208,0.0002486366,0.001495049,0.0002979368,0.004489801,0.00002507833,0.00005878511,0.007452962,0.0001137421,0.00001269152,0.9851546,0.00006205455],"study_design_scores_gemma":[0.0005490023,0.0001135379,0.004996879,0.00006986158,0.003638536,0.000002376356,0.0009913277,0.01916195,0.00006863776,0.00004977069,0.9697129,0.0006452421],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.000453876,0.0006902577,0.0001445886,0.0009482304,0.0005086558,0.006371409,0.9906675,0.000118245,0.00009728761],"genre_scores_gemma":[0.00158176,0.0001288552,0.0003553764,0.0001563153,0.002234524,0.003543129,0.989404,0.0003240658,0.00227196],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.03736496,"threshold_uncertainty_score":0.9997959,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1589014451028148,"score_gpt":0.4038139880482954,"score_spread":0.2449125429454805,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}